|Publication number||US5041976 A|
|Application number||US 07/399,683|
|Publication date||20 Aug 1991|
|Filing date||28 Aug 1989|
|Priority date||18 May 1989|
|Publication number||07399683, 399683, US 5041976 A, US 5041976A, US-A-5041976, US5041976 A, US5041976A|
|Inventors||Kenneth A. Marko, John V. James, James M. Dosdall|
|Original Assignee||Ford Motor Company|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (25), Non-Patent Citations (9), Referenced by (187), Classifications (15), Legal Events (4)|
|External Links: USPTO, USPTO Assignment, Espacenet|
This application is a continuation of application Ser. No. 07/353,726, filed May 18, 1989, now abandoned.
The present invention relates in general to the identification of the operating condition of an internal combustion engine including fault conditions in the engine, and more specifically to the use of a pattern recognition system examining engine operating parameters to identify specific fault conditions in the engine.
Automotive control systems for internal combustion engines can include an electronic engine control for improved reliability, advanced functionality, and low cost. A typical electronic system includes a master engine controller and a plurality of sensors and actuators incorporated into the powertrain of a vehicle. The master engine controller processes data from the sensors using look-up tables and complex algorithms in order to determine appropriate commands for the actuators. For example, engine position, engine speed, throttle position, and exhaust gas oxygen content can be monitored in order to determine a proper spark timing and dwell for engine operation. The particular strategy employed is designed to achieve compliance with federal emission regulations while optimizing fuel economy and powertrain performance.
In addition to engine controls, several other automotive systems currently employ or are candidates for electronic controls. Such systems include anti-lock brakes, drive by wire systems, and transmission control.
Operation of these electronic control systems must be highly reliable for safety reasons. When a fault develops, it must be possible to trace the cause of the fault to the plant (i.e., powertrain), the controller, or its sensors or actuators.
Due to the inherent complexity of electronic control systems, the task of diagnosing a fault becomes very difficult. Therefore, a great deal of effort has been expended in searching for diagnosis methods which require a minimum of skill or knowledge of the service technician.
Prior art attempts to provide electronic engine control fault diagnosis have involved computerization in order to minimize the skill required to perform the diagnosis. For instance, a data acquisition system can be used to provide engine operating information to a computer which compares the information to prespecified normal data. The measured values are compared with preset reference values in order to find discrepancies which indicate possible faults. Some systems also apply specific algorithms to measured values in order to determine specific engine characteristics. For example, the computer may determine an integrated average over time or may extract particular features of a waveform for analysis.
Several prior art engine diagnosis systems have employed the use of an expert system which is a rule based system for analyzing input engine parameters according to rules describing the controlled system developed by an expert. An expert system requires an intense learning process by the expert to understand the system and to codify his knowledge into a set of rules. Thus, expert system development takes a large amount of time and resources. An expert system is not responsive to frequent design changes such as occur in automotive development. A change in engine design changes the rules, which requires the expert to determine the new rules and to redesign the system.
U.S. Pat. No. 4,252,013, issued to Hyanova et al, discloses a diagnostic system for an internal combustion engine in which pick-up devices sense engine parameters. Dynamic input signals are preprocessed in order to provide quasi-static indices of engine conditions. The preprocessed signals and other measured signals are applied to predetermined algorithms to give diagnostic indices of the internal combustion engine.
U.S. Pat. No. 4,375,672, issued to Kato et al, discloses a computerized engine analyzer for making automatic diagnosis. Sensors connected to an internal combustion engine detect characteristics of the engine. The signals from the sensors are preprocessed and are then compared in a computer with a preset program corresponding to the engine. The results of various diagnoses of the engine are indicated as the diagnosis proceeds under control of an operator.
U.S. Pat. No. 4,418,388, issued to Allgor et al, discloses an engine analyzer which measures engine operating parameters including electrical system waveforms which are then stored in the memory. The stored waveforms are compared to analytical matrices dictated by engine type. Based on the preprogrammed relationship of matrix locations and the input waveforms, information is processed to identify defective systems.
U.S. Pat. No. 4,424,709, issued to Meier Jr. et al, discloses an engine analyzer for identifying engine defects based on signals from various sensors. The detected signals are compared with signals from normal engines in the frequency domain. By recognizing specific differences, or looking for abnormal frequency components, engine defects are identified.
An expert system for car fault diagnosis is described in Armano et al, Empirical And Functional Knowledge In An Expert System For Fault Diagnosis, IEEE International Workshop on Artificial Intelligence for Industrial Applications, pages 109-114 (1988). The expert system architecture disclosed in this paper uses artificial intelligence techniques to incorporate both empirical knowledge and functional knowledge to reach a fault diagnosis.
The use of failure detection filters to diagnose automotive control systems is disclosed in Liubakka et al, Failure Detection Algorithms Applied To Control System Design For Improved Diagnostics And Reliability, SAE Technical Paper Series, Paper No. 880726 (1988). The failure detection and isolation method disclosed employs a system model for predicting system operation. Known relationships between system inputs and outputs allow the diagnostic system to anticipate a system output given detected system inputs. Any difference between the predicted system outputs and those detected by the sensors indicates a system fault.
Each of the prior art diagnostic systems requires predetermined engine analytical information in order to design a system to detect faults. As electronic systems increase in complexity, the determination of such analytical information becomes more difficult, time-consuming, and expensive. These are some of the problems this invention overcomes.
It is a principal object of the present invention to diagnose operation of an electrical control system without requiring detailed analytical modeling of the system.
It is another object of this invention to provide a diagnostic system for detecting faults in complicated electronic control systems which is inexpensive to develop and provides accurate results.
It is a further object of the invention to provide a method for identifying selected conditions in a combustion engine using pattern recognition and for training a pattern recognition system to recognize the selected conditions.
It is still another object of the invention to provide an apparatus for identifying possible fault conditions in an internal combustion engine by employing a pattern recognizer which can be easily adapted to different engines.
These and other objects are achieved using a method for identifying selected conditions in an electronically controlled automotive system wherein a trainable pattern recognition system (such as a neural network) is employed according to the teachings of the invention. Specifically, a plurality of system operating trials are conducted using a test system, each trial including at least one respective one of a plurality of known selected conditions, such as fault conditions. System operating data is collected during the operating trials corresponding to a plurality of system parameters, the parameters including signals passing to and from an electronic control and calculated quantities derived therefrom. In the embodiment where the controlled system is a combustion engine, the parameters include measurements and calculations for each individual firing event during operation of the engine. System parameters and corresponding known system fault identities are input as training vectors to the pattern recognition system. During training, the pattern recognition system learns to correlate patterns in the system parameters with respective system faults. Subsequently, a system operating trial is conducted using a system to be diagnosed. The system diagnostic data corresponding to the system parameters is collected and the parameters based on the diagnostic data are input as input vectors to the pattern recognition system to identify those selected conditions which are present in the operation of the system to be diagnosed.
The invention further includes apparatus, for identifying possible fault conditions in an automotive system, that comprises monitor means, processing means, memory means, and pattern recognition means. The monitor means is adapted to be coupled to the system for collecting a plurality of time referenced values corresponding to selected system parameters during operation of the system, the parameters including signals passing to and from the system. The processing means is coupled to the monitor means for processing the values to derive system parameters and organizing the system parameters into vectors. The memory means is coupled to the processing means for storing the vectors. The pattern recognition means is coupled to the memory means for classifying the stored vectors according to the possible fault conditions. The time referenced values may include digital values and analog values, the digital values being monitored upon occurrence of a transition therein, and the analog value being monitored at predetermined intervals.
The novel features of the invention are set forth with particularity in the appended claims. The invention itself, however, both as to its organization and method of operation, together with further objects and advantages thereof, may best be understood by reference to the following description taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a functional block diagram showing a pattern recognition system during training to recognize selected conditions in an engine.
FIG. 2 is a functional block diagram showing detection of the selected conditions in an engine to be diagnosed by a trained pattern recognition system.
FIG. 3 is a block diagram showing a data acquisition system connected to an engine and its electronic control.
FIG. 4 is a block diagram showing the data acquisition means as part of a computerized fault detection system of the invention in greater detail.
FIG. 5 is a functional block diagram showing processing of engine operating data to generate engine parameters for applying to the pattern recognition system.
FIG. 6 is a matrix of parameter vectors for application to a pattern recognition system.
FIG. 7 is a block diagram showing the inputs and outputs for the pattern recognizer of the invention.
FIG. 8 illustrates the matrix of combinations of parameter vectors and condition classification codes during training of the pattern recognition system.
The present invention enables diagnosis of faults in a variety of electronically controlled electromechanical systems. Fault diagnosis is performed as a passive observer of system operation using only the information that is available within the system while it is operating. Furthermore, by proper selection of system parameters to be observed, high accuracy in failure detection is achieved by means of a pattern recognition system. The preferred embodiment and best mode of the invention specifically relates to fault diagnosis in an electronically controlled internal combustion engine, as is described below.
The electronically controlled internal combustion engine is a complex system in which high speed analog and digital signals are sent to and from the electronic control during engine operation. Some characteristics of a high speed data acquisition system for collecting the analog and digital data from sensors and actuators in an electronically controlled engine are given in James et al, Microprocessor Based Data Acquisition For Analysis Of Engine Performance, SAE Technical Paper Series, Paper No. 870386 (1987).
The amount of data collected by such a data acquisition system, even during a single engine cycle, is very large. Furthermore, the variations between data from normal engine operation and faulty engine operation can be subtle. Therefore, it can be very difficult to train a technician to associate each pattern with a specific engine fault. Likewise, developing an explicit algorithmic computer program or creating an expert system to perform the association can only be done with great effort and expense.
In accordance with the present invention, a pattern recognition system such as a neural network simulation program used in conjunction with the high speed data acquisition system can produce a diagnostic system which can be trained to correlate signatures of improper engine performance with causes of faults. During training of the pattern recognition system, an engine is operated in a service bay with known faults, i.e. bugs, with each operating trial being tagged according to the fault introduced. Data from a normal (i.e., unbugged) engine is also included. Subsequently, an engine operating with a previously unidentified fault can be identified using the trained system.
Referring now to FIG. 1, an automobile 10 includes an electronically controlled engine 11. Operating data in the form of electrical signals associated with an electronic controller in engine 11 are collected by a data acquisition unit 12 which provides the operating data to a data analysis and formatting unit 13. At least one parameter vector is provided from unit 13 to a pattern recognizer 14 in conjunction with an engine condition classification from a classification unit 15. Pattern recognizer 14 is coupled to a data base 16 which is built up during training of the system.
FIG. 2 corresponds to operation of the diagnostic system after training for the purpose of identifying the condition of an engine. An automobile 20 includes an electronically controlled engine 21 to be diagnosed which is substantially identical to engine 11 which was employed during training. Diagnostic operating data is obtained by data acquisition unit 12 and provided to data analysis and formatting unit 13. A diagnostic parameter vector is provided to pattern recognizer 14 which classifies the vector according to the trained data base 16. A classification output is provided at 17 corresponding to the attempted classification of the operating condition of engine 21.
Functional blocks 13-17 of FIGS. 1 and 2 can preferably be implemented with a computer such as a PC or an on-board microcomputer, such as in the electronic engine control itself.
The training of the system, as shown in FIG. 1, requires the compilation of a large data base from test engine 11 which is first monitored while operating properly and then with known "bugs" created by a technician. The technician creates various faults in the vehicle while the computer acquires, analyzes, and formats the results for inclusion in the data base, along with a coded classification of the particular cause of the fault, provided by the technician.
The operating data acquired from the engine can be used in calculations to determine exact engine operating parameters. The parameters and the fault classifications are formatted as multidimensional vectors. Preferably, each parameter vector contains at least 52 performance parameters for a single cycle of a six cylinder engine. Since statistical fluctuations can cause variations in exact parameter values, preferably at least 16 vectors are stored for each test condition of engine 11. The utility and accuracy of the system is strongly influenced by the representation chosen both for fault identification codes generated as output during diagnosis and for engine operating parameters used in the parameter vector's input to pattern recognizer 14. Using the particular engine parameters and the selected fault conditions described below, not only the engine cylinder at fault but also the nature of the fault, including indications of faulty components and indication of components that are functioning properly, can be obtained. The diagnostic system is very precise in identifying faults and accomplishes the identification of multiple simultaneous faults under many conditions.
Continuing with the operation of the system shown in FIGS. 1 and 2, after a large data base of fault information has been gathered and formatted by data analysis and formatting unit 13, pattern recognizer 14 and data base 16 undergo training. During training, the system recursively adjusts its internal structure until the system has learned the proper association between parameter vectors from an engine and fault classifications introduced through the classification input. The trained system parameters are saved in data base 16 and the trained system may then be presented with new data from engine 21. No classification input is presented to the system, since the system is expected to classify the new data according to previous classifications. The classification output from the system can be an indication of proper engine operation, an identification of one or more classified conditions which were introduced during training, or an indication of an inability to recognize any trained condition.
For powertrain diagnostics, the data acquired from the vehicle is based upon the signals communicated between the on-board electronic engine control (EEC) and the powertrain (engine). The set of signals captured for analysis is based upon a determination of the information that is necessary for accurate diagnosis and upon the ability of the data acquisition system to acquire and store the signals. The information used for data acquisition, training and diagnosis preferably includes the following signals and calculated parameters:
The engine crankshaft position is sensed by the Profile Ignition Pickup (PIP) sensor located on the distributor shaft. The PIP signal is a digital signal which changes level at 10 degrees before top-dead-center (10° BTDC) on each firing cylinder for every engine cycle (two complete revolutions of the crankshaft for a 4-stroke engine). PIP is the primary source of information about engine performance during each cycle, since we can derive the parameters of crankshaft velocity and acceleration from it by taking the appropriate derivatives. In another embodiment, this signal is derived from a sensor directly monitoring the crankshaft with a higher sampling rate. The greater accuracy of a high data rate sensor improves sensitivity of the system in detecting engine roughness caused by faulty components.
Based on the PIP signal, engine speed in revolutions per minute is calculated as an engine parameter.
Based on the PIP signal or a high data rate position sensor, engine acceleration averaged over one engine cycle is calculated. Preferably, the average is determined as a median filtered value.
Engine acceleration during an individual cylinder firing is calculated and the difference taken from the average acceleration during the engine cycle. This parameter gives information about misfiring cylinders.
This signal is an output from the EEC which controls the time of firing of the individual spark plugs. It is calculated by the EEC in a manner to maximize fuel economy within emissions constraints. Monitoring this signal provides an indication of proper operation of the spark strategy including the calculated parameter of actual spark advance for each cylinder firing.
This signal is obtained from the primary of the ignition coil. The shape of this signal and its timing provides information on dwell (the length of time the coil is being charged) and on arc duration (the length of time a spark is present in the spark plug gap). Analysis of these signals in conjunction with the SPOUT signal provides diagnostic information about the ignition system and its operation.
This signal is an indication of the airflow into the engine and is based upon a sensor whose output typically is a frequency linearly related to the pressure in the intake manifold.
On some newer vehicles, airflow into the engine is measured directly by this sensor, rather than inferred from manifold pressure (MAP) and other parameters. The output of this sensor may be an analog voltage whose value is proportional to the mass of air flowing into the engine.
An analog voltage output from this sensor provides information on the temperature of the incoming air and is used by the EEC to estimate the air density in calculating the amount of air flowing into the engine.
This sensor monitors the position of the vane controlling air admission to the engine under the command of the driver through the linkage to the accelerator pedal. It is an analog voltage proportional to the degree of throttle opening.
This signal is derived from a pressure sensor on the exhaust side of the exhaust gas recirculation (EGR) valve which is controlled by the electronic vacuum regulator (EVR) signal from the EEC. Correlating this PFE signal with the EVR controlling signal from the EEC can be used to diagnose improper operation of the EGR system, as well as to detect the presence of other engine faults such as defective valves.
These signals are delivered to the fuel injectors and control the timing and the amount of fuel (pulse width) delivered to each cylinder. These signals provide timing and pulse with information to diagnose the operation of the fuel delivery system.
This sensor has an output which is substantially binary in its response to the presence or absence of oxygen in the exhaust gas. Proper system operation regulates the engine so that the mixture is, on average, neither rich nor lean. When the mixture transits from rich to lean, the output of this sensor changes abruptly. The output of this sensor is used by the EEC to control the mixture ratio so that the sensor is constantly switching between its two states, indicating that the mixture is near stoichiometric.
This signal from the EEC is a duty cycle modulated pulse which opens an air bypass valve against a spring to regulate the idle speed of the vehicle. Correlating the ISC signal with the idle speed variations and MAP provides a means of diagnosing faults in the ISC system.
This is the output of a sensor in the cooling fluid in the engine which is an analog voltage proportional to the cooling system temperature. This signal is used in the EEC control system to activate a cold engine strategy and to control the cooling system to maintain proper engine temperature after warm-up.
This is the output of a sensor used in some high performance engines to detect the presence of engine knock. The signal is used to regulate the spark timing to avoid continuous engine knock which could damage the engine if it continued for long periods of time.
This sensor provides an output proportional to the driveshaft speed for regulating vehicle speed by speed-control system, often incorporated into the EEC.
This is an EEC signal proportional to the battery voltage in the car.
Turning now to FIG. 3, the connection of data acquisition system 12 to an electronically controlled engine is shown for rapidly gathering the large amount of data required to assess vehicle performance. An engine 26 includes a plurality of sensors 28 and a plurality of actuators 29. An electronic engine control (EEC) 25 communicates with sensors 28 and actuators 29 over communication lines 27. Data acquisition system 12 monitors signals on lines 27 by means of a plurality of signal lines 30. Data acquisition system 12 acquires and stores signals being communicated to and from EEC 25 at a sufficiently high rate such that various parameters of engine performance at the actual level of firing events can be determined. One possible approach for acquiring engine data suitable for the present invention is discussed in the paper James et al, Microprocessor Based Data Acquisition For Analysis Of Engine Performance, SAE Technical Paper Series, Paper No. 870386 (1987), mentioned earlier.
A preferred embodiment for implementing data acquisition system 12 is shown in FIG. 4. Data is acquired and stored according to a timestamping procedure. As described in the above-referenced article, timestamping of digital signals only records changes which occur on any of the lines being monitored along with the time that the change occurs.
As shown in FIG. 4, the signal acquisition lines 30 are separated according to digital signals and analog signals. The digital signals are coupled to a timestamping board 31 including clock 33 and latches 34. Latches 34 are coupled via output lines 35 to a digital interface 36 in a microcomputer 32. Analog signals from lines 30 are coupled to an analog interface 39 also in microcomputer 32. Digital interface 36 and analog interface 39 are each coupled to a direct memory access (DMA) unit 37 which controls direct memory transfer to a random access memory (RAM) 38. A selected digital line from digital signals 30 is connected to analog interface 39 over a line 45 for acting as a trigger of analog measurements as discussed below.
In operation, digital signals from lines 30 are monitored by latches 34 such that the previously timestamped values (or initial values taken when monitoring begins) are compared with the current values. Upon a change in any digital value, a new timestamped output consisting of the value of each digital line (or identification of the line or lines that changed) is output over lines 35 along with the clock value at the time the change occurred. The new timestamped digital values are processed by digital interface 36 and transferred via DMA 37 such that the values and time signature are stored in RAM 38 in substantially real-time. Preferably, the transfer of timestamped data occurs at a speed which allows a resolution in timestamped data of about two microseconds.
Analog signals from lines 30 are likewise stored in association with a timestamping signal. According to the present embodiment, analog signals are measured upon each occurrence of a particular substantially periodic digital signal from the digital lines 30. In particular, for electronically controlled engine applications, the trigger for taking analog measurements is preferably a transition of an engine position signal such as the PIP described earlier. In response to the trigger pulse on line 45, analog interface 39 samples a plurality of analog signals substantially simultaneously. They are then converted to digital signals by analog-to-digital converters within the interface. The digitized signals are provided via DMA 37 and are stored in RAM 38 in association with the digital timestamped signals occurring simultaneously. Thus, the analog signals can be correlated to the clock reading coinciding with the digital timestamped output including the trigger pulse. Once a sufficient amount of data is contained in RAM 38, microcomputer 32 is free to process the data in order to calculate various engine operating parameters or other values. Such processing may begin after completion of data acquisition or may be performed concurrently with data acquisition in order to diagnose engine conditions in real time.
Subsequent processing of data can be performed according to the diagram in FIG. 5. Time-referenced data 40 can be input to a number of calculations 41. The output of calculations 41 and some unchanged data (e.g., from analog sensors) are input to a formatting section 42 which operates to organize the engine operating data and parameters into a parameter vector appropriate for input to the pattern recognition system.
FIG. 6 shows a plurality of training vectors for training of the pattern recognition system. A first parameter vector Xl consists of a plurality of individual parameter values xl,l to xl,n FIG. 6 shows m parameter vectors (Xl to Xm) where m is a sufficient number to adequately train the pattern recognition system to accurately recognize the preselected conditions. The individual parameter values xl to xn are preferably comprised of the parameters discussed above, including cylinder number, engine speed, acceleration, spark timing, spark duration, dwell, mass airflow, throttle position, feedback exhaust gas recirculation pressure, fuel injector pulse width, exhaust gas oxygen content, idle speed control duty factor, engine temperature, knock, vehicle speed, and battery voltage. Each parameter corresponds to an individual firing event, i.e., to a particular PIP signal. Although some of the digital signals obtained from timestamping are synchronous with the PIP signal, most are not. All digital transmissions are collected as they occur, but in post-processing, the relevant engine parameters are calculated from the digital signals associated with the PIP interval nearest in time. The parameters are determined once per engine firing, and information from several engine firings provides the plurality of training vectors Xl to Xm. Some parameters known to be slowly varying (e.g., various temperatures) can be averaged over the full engine cycle to yield a single value for inclusion into a vector in order to avoid unnecessarily large vectors.
Multiple sets of training vectors Xl to Xm are obtained corresponding to selected engine operating conditions. Each set corresponds to either normal operation or operation under a fault condition. As shown in FIG. 7, pattern recognizer 14 receives a parameter vector X simultaneously with a condition code C during training. When m is equal to 16, then 16 parameter vectors X will be presented to pattern recognizer 14 along with a single condition code C. For the next operating condition being presented to pattern recognizer 14, a different set of 16 parameter vectors X are presented simultaneously with a new condition code C. Once training is complete, only a single parameter vector X need be presented to pattern recognizer 14 which then outputs one or more condition codes C corresponding to engine conditions recognized within the parameter vector.
FIG. 8 shows the combination of inputs to pattern recognizer 14 for training on a number of conditions Cl to Cy. For example, an electronically controlled engine is operated under a first fault condition C1. Preferably, the engine is operated at a steady speed. Data is obtained corresponding to a plurality of engine firings sufficient to construct m parameter vectors. Next, the engine is operated with a new induced fault C2 while timestamped data is obtained to construct a new set of parameter vectors Xl to Xm. The process is repeated until the last fault or normal operating condition Cy is obtained.
Once the full set of parameter vectors is completed, they are mated to their corresponding condition code as shown in FIG. 8 and presented to pattern recognizer 14. For improved speed and accuracy of training, it is preferable to present the training vectors to pattern recognizer 14 in a randomized order, i.e., not all of the vectors corresponding to a respective fault condition are presented sequentially. The internal reorganization of the pattern recognition data base converges to a proper configuration more efficiently when such a random order of vectors is used. Furthermore, several passes through the sets of vectors may be required to achieve a desired level of accuracy.
Preferably, the operating conditions for which training occurs on an electronically controlled engine includes both cylinder specific faults, cylinder independent faults, and a normal operating condition. The cylinder specific faults preferably include, at least, a shorted spark plug, an open spark plug, and a clogged fuel injector. Cylinder independent faults preferably include a shorted manifold absolute pressure sensor, an open manifold absolute pressure sensor, a shorted exhaust gas oxygen sensor, an open exhaust gas oxygen sensor, and idle speed control duty cycle faults. Additional fault conditions can include intake and exhaust valve train faults such as valves open or closed, head gasket leaks, partial clogging of fuel injectors, fouled spark plugs, uneven air/fuel mixture among cylinders, and improper fuel injection phasing. Although parameter vectors are conveniently collected for each fault in isolation, it is possible for pattern recognizer 14 to identify simultaneous fault occurrences even though no training data was taken with simultaneous occurrence of the same faults. Furthermore, with proper training, the system recognizes and identifies a specific cylinder where a cylinder specific fault has occurred.
The present invention has been implemented for a six-cylinder electronically controlled engine. A parameter vector including 52 individual parameters (both one-per-firing and once-per-cycle) was used. In this implementation, 26 different operating conditions (both cylinder specific and non-cylinder specific) were observed with the engine operating at about 1000 rpm. The training set consisted of 16 parameter vectors for each condition (e.g., failure) introduced. After training, as little as one parameter vector from an engine to be diagnosed is all that is required by the pattern recognizer for correct classification.
In a preferred embodiment, the pattern recognizer system included a backpropagation method for learning patterns and classifications. Such mathematical pattern recognition algorithms are well known in the art. In another preferred embodiment, the pattern recognizer comprised the Nestor NDS-1000 System available from Nestor Incorporated, New York, New York. After complete training, the Nestor system obtained 100% accuracy in identifying the operating condition of an engine being diagnosed.
In implementing the entire system using pattern recognition software, a microcomputer is employed for linking computer recognition software (e.g., a backpropagation program or the Nestor software) into a larger program which performs data acquisition and data formatting and preparation, such as cycle binning, normalization, and scaling. Although the time for manually collecting parameters according to all the engine conditions to be recognized can take several hours, the training vectors are learned by the pattern recognition system in about 5-10 minutes. This, faults are then reintroduced at a later time and can be recognized by the system of the present invention without any modeling or other detailed knowledge of the operation of the engine system. Any modification to the engine requires that new data be taken and the system be retrained. However, the reformulation of detailed rules which would be required by an expert system are avoided.
The present invention has been implemented using primarily commonly available hardware and software. Thus, an effective and efficient technique has been provided for proper diagnosis of electronic systems. Furthermore, the system is readily transferable to systems on-board an electronic engine control for continuous diagnosis of engine operation in a vehicle.
Although the separate sensing of signals passing to and from an EEC has been shown in the preferred embodiment, many of the calculated values may be available from calculations being performed in the EEC itself (e.g., spark timing and RPM). Rather than duplicate such calculations, it is possible to obtain these parameters from the ECC over a data communication link or other data port if one is provided in the EEC. Another possible modification of the invention involves the use of a vector which contains information from multiple cycles. This allows additional fault conditions to be recognized such as idle hunting.
While preferred embodiments of the invention have been shown and described herein, it will be understood that such embodiments are provided by way of example only. Numerous variations, changes, and substitutions will occur to those skilled in the art without departing from the spirit of the invention. Accordingly, it is intended that the appended claims cover all such variations as fall within the spirit and scope of the invention.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US3950733 *||6 Jun 1974||13 Apr 1976||Nestor Associates||Information processing system|
|US4125894 *||18 May 1977||14 Nov 1978||Sun Electric Corporation||Engine test and display apparatus|
|US4128005 *||16 Jun 1977||5 Dec 1978||Sun Electric Corporation||Automated engine component diagnostic techniques|
|US4215404 *||12 Sep 1978||29 Jul 1980||Alt Viktor V||Automatic device for diagnostic checkup of vehicles|
|US4228679 *||10 Apr 1979||21 Oct 1980||Alt Viktor V||Apparatus for measuring parameters of work diagram of piston machines|
|US4234921 *||27 Jun 1978||18 Nov 1980||Tokyo Shibaura Denki Kabushiki Kaisha||Tester for electronic engine control systems|
|US4252013 *||13 Aug 1979||24 Feb 1981||Ckd Praha, Oborovy Podnik||Arrangement for complex diagnosis of internal combustion engines|
|US4254474 *||2 Aug 1979||3 Mar 1981||Nestor Associates||Information processing system using threshold passive modification|
|US4270174 *||5 Feb 1979||26 May 1981||Sun Electric Corporation||Remote site engine test techniques|
|US4295363 *||25 Mar 1977||20 Oct 1981||Harris Corporation||Apparatus for diagnosing faults in individual cylinders in an internal combustion engine|
|US4319331 *||28 Jan 1980||9 Mar 1982||Nestor Associates||Curve follower|
|US4326259 *||27 Mar 1980||20 Apr 1982||Nestor Associates||Self organizing general pattern class separator and identifier|
|US4375672 *||5 May 1980||1 Mar 1983||K.K. Toyota Chuo Kenkyusho, Et Al.||Engine analyzer|
|US4394742 *||31 Oct 1980||19 Jul 1983||Fmc Corporation||Engine generated waveform analyzer|
|US4418388 *||14 Aug 1980||29 Nov 1983||The Allen Group Inc.||Engine waveform pattern analyzer|
|US4424709 *||6 Jul 1982||10 Jan 1984||Ford Motor Company||Frequency domain engine defect signal analysis|
|US4566073 *||28 Dec 1982||21 Jan 1986||United Technologies Corporation||Soft category classifier|
|US4730259 *||1 Mar 1985||8 Mar 1988||Gallant Stephen I||Matrix controlled expert system producible from examples|
|US4760604 *||12 Sep 1985||26 Jul 1988||Nestor, Inc.||Parallel, multi-unit, adaptive, nonlinear pattern class separator and identifier|
|US4773028 *||1 Oct 1984||20 Sep 1988||Tektronix, Inc.||Method and apparatus for improved monitoring and detection of improper device operation|
|US4796206 *||2 Jun 1986||3 Jan 1989||International Business Machines Corporation||Computer assisted vehicle service featuring signature analysis and artificial intelligence|
|US4839811 *||21 Sep 1987||13 Jun 1989||Nissan Motor Company Limited||Automotive vehicle trouble checking apparatus|
|US4849894 *||12 Dec 1986||18 Jul 1989||Bayerische Motoren Werke A.G.||Process for determining operating conditions of a motor vehicle from the output signals of a sensor for a relevant operating variable|
|US4866635 *||19 Oct 1987||12 Sep 1989||Carnegie Group Inc.||Domain independent shell for building a diagnostic expert system|
|US4912655 *||14 Dec 1988||27 Mar 1990||Gte Laboratories Incorporated||Adjusting neural networks|
|1||"Empirical and Functional Knowledge in an Expert System for Fault Diagnosis", G. Armano et al., International Workshop on Artifical Intelligence for Industrial Applications 1988, pp. 109-114.|
|2||"Failure Detection Algorithms Applied to Control System Design for Improved Diagnostics and Reliability", SAE Technical Paper Series #880726 (1988).|
|3||"Microprocessor Based Data Acquisition for Analysis of Engine Performance", SAE Technical Paper Series #870386 (1987).|
|4||*||Empirical and Functional Knowledge in an Expert System for Fault Diagnosis , G. Armano et al., International Workshop on Artifical Intelligence for Industrial Applications 1988, pp. 109 114.|
|5||*||Failure Detection Algorithms Applied to Control System Design for Improved Diagnostics and Reliability , SAE Technical Paper Series 880726 (1988).|
|6||*||Microprocessor Based Data Acquisition for Analysis of Engine Performance , SAE Technical Paper Series 870386 (1987).|
|7||*||Nestor Development System (NDS 1000) Reference Manual, 1987, pp. 1.1 to 6.8.|
|8||*||Philip D. Wasserman; Neural Computing Theory and Practice 1989, pp. 43 56.|
|9||Philip D. Wasserman; Neural Computing-Theory and Practice 1989, pp. 43-56.|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US5122976 *||12 Mar 1990||16 Jun 1992||Westinghouse Electric Corp.||Method and apparatus for remotely controlling sensor processing algorithms to expert sensor diagnoses|
|US5193513 *||3 Jun 1992||16 Mar 1993||Ford Motor Company||Misfire detection in an internal combustion engine using exhaust pressure|
|US5200898 *||15 Nov 1990||6 Apr 1993||Honda Giken Kogyo Kabushiki Kaisha||Method of controlling motor vehicle|
|US5203300 *||28 Oct 1992||20 Apr 1993||Ford Motor Company||Idle speed control system|
|US5214582 *||30 Jan 1991||25 May 1993||Edge Diagnostic Systems||Interactive diagnostic system for an automotive vehicle, and method|
|US5215055 *||28 Oct 1992||1 Jun 1993||Ford Motor Company||Idle speed and fuel vapor recovery control system|
|US5228421 *||28 Oct 1992||20 Jul 1993||Ford Motor Company||Idle speed control system|
|US5285523 *||24 Sep 1991||8 Feb 1994||Nissan Motor Co., Ltd.||Apparatus for recognizing driving environment of vehicle|
|US5287282 *||25 Jun 1991||15 Feb 1994||Fuji Jukogyo Kabushiki Kaisha||Misfire diagnosis apparatus for an internal combustion engine|
|US5311421 *||10 Dec 1990||10 May 1994||Hitachi, Ltd.||Process control method and system for performing control of a controlled system by use of a neural network|
|US5361213 *||24 Mar 1993||1 Nov 1994||Hitachi, Ltd.||Control device for an automobile|
|US5361628 *||2 Aug 1993||8 Nov 1994||Ford Motor Company||System and method for processing test measurements collected from an internal combustion engine for diagnostic purposes|
|US5365438 *||8 Jan 1993||15 Nov 1994||Ford Motor Company||Audible and visual feedback for user stimulated self-test diagnostics|
|US5394327 *||27 Oct 1992||28 Feb 1995||General Motors Corp.||Transferable electronic control unit for adaptively controlling the operation of a motor vehicle|
|US5412584 *||30 Nov 1993||2 May 1995||Kabushiki Kaisha Toyota Chuo Kenkyusho||Dynamic system diagnosing apparatus, tire air pressure diagnosing apparatus and vehicle body weight change detecting apparatus using same|
|US5414645 *||23 Oct 1992||9 May 1995||Mazda Motor Corporation||Method of fault diagnosis in an apparatus having sensors|
|US5438513 *||19 Nov 1993||1 Aug 1995||Chrysler Corporation||Automotive electronics test system|
|US5483936 *||5 Jul 1994||16 Jan 1996||Kerstein; Scott M.||Spark knock detection system for an internal combustion engine|
|US5486998 *||14 Jun 1993||23 Jan 1996||Amax Coal West, Inc.||Process stabilizing process controller|
|US5495415 *||18 Nov 1993||27 Feb 1996||Regents Of The University Of Michigan||Method and system for detecting a misfire of a reciprocating internal combustion engine|
|US5561600 *||3 Aug 1995||1 Oct 1996||Chrysler Corporation||Dual sensor misfire detection apparatus and method for an internal combustion engine|
|US5577166 *||20 Jul 1992||19 Nov 1996||Hitachi, Ltd.||Method and apparatus for classifying patterns by use of neural network|
|US5583771 *||4 Aug 1994||10 Dec 1996||Delco Electronics Corp.||Method and apparatus for distinguishing between deployment events and non-deployment events in an SIR system|
|US5631831 *||8 Aug 1995||20 May 1997||Spx Corporation||Diagnosis method for vehicle systems|
|US5642284 *||12 Aug 1994||24 Jun 1997||Caterpillar Inc.||Maintenance monitor system|
|US5687082 *||22 Aug 1995||11 Nov 1997||The Ohio State University||Methods and apparatus for performing combustion analysis in an internal combustion engine utilizing ignition voltage analysis|
|US5699253 *||5 Apr 1995||16 Dec 1997||Ford Global Technologies, Inc.||Nonlinear dynamic transform for correction of crankshaft acceleration having torsional oscillations|
|US5734569 *||7 Sep 1994||31 Mar 1998||Snap-On Technologies, Inc.||Computer interface board for electronic automotive vehicle service equipment|
|US5740352 *||27 Sep 1995||14 Apr 1998||B-Tree Verification Systems, Inc.||Liquid-crystal display test system and method|
|US5752213 *||29 Feb 1996||12 May 1998||Ford Global Technologies, Inc.||Misfire detector with torsional oscillation filtering|
|US5761626 *||26 Dec 1995||2 Jun 1998||Ford Global Technologies, Inc.||System and method for distinguishing and characterizing motor vehicles for control of automatic drivers|
|US5781700 *||5 Feb 1996||14 Jul 1998||Ford Global Technologies, Inc.||Trained Neural network air/fuel control system|
|US5794171 *||29 Feb 1996||11 Aug 1998||Ford Global Technologies, Inc.||Process for deriving predictive model of crankshaft rotation of a combustion engine|
|US5809437 *||7 Jun 1995||15 Sep 1998||Automotive Technologies International, Inc.||On board vehicle diagnostic module using pattern recognition|
|US5835901 *||30 Jul 1997||10 Nov 1998||Martin Marietta Corporation||Perceptive system including a neural network|
|US5854990 *||6 Jun 1996||29 Dec 1998||Daimler-Benz Ag||Process and apparatus for controlling the combustion course in an Otto combustion engine|
|US5941926 *||10 Apr 1996||24 Aug 1999||Snap-On Technologies, Inc.||Engine analyzer with cylinder triggering of oscilloscope display having fixed-time sweep|
|US5978727 *||15 Mar 1996||2 Nov 1999||Sun Electric U.K. Limited||Method and apparatus for engine analysis by waveform comparison|
|US5999867 *||30 Jul 1997||7 Dec 1999||Snap-On Technologies, Inc.||Computer interface board for electronic automotive vehicle service equipment|
|US6006147 *||30 Jun 1997||21 Dec 1999||Chrysler Corporation||Translator and voltage check module for hand-held vehicle tester|
|US6006156 *||11 Dec 1997||21 Dec 1999||Cummins Engine Company, Inc.||Apparatus and method for diagnosing and controlling an ignition system of an internal combustion engine|
|US6026344 *||13 Feb 1997||15 Feb 2000||Spx Corporation||Diagnosis method for vehicle systems|
|US6064996 *||29 Sep 1997||16 May 2000||Yamaha Hatsudoki Kabushiki Kaisha||Evolutionary controlling system with behavioral simulation|
|US6073088 *||23 Jan 1998||6 Jun 2000||Schlumberger Technologies, Inc.||EMS testing system|
|US6085732 *||25 Jan 1999||11 Jul 2000||Cummins Engine Co Inc||EGR fault diagnostic system|
|US6092018 *||5 Feb 1996||18 Jul 2000||Ford Global Technologies, Inc.||Trained neural network engine idle speed control system|
|US6112150 *||9 Apr 1999||29 Aug 2000||Cummins Engine Co Inc||Fault recognition system and method for an internal combustion engine|
|US6138109 *||23 Dec 1997||24 Oct 2000||Caterpillar Inc.||Neural network diagnostic classification of complex binary systems|
|US6138349 *||18 Dec 1997||31 Oct 2000||Vlt Corporation||Protective coating for an electronic device|
|US6163250 *||31 Aug 1999||19 Dec 2000||International Business Machines Corporation||System and method for sensing objects on surface of vehicle|
|US6175787||20 Aug 1998||16 Jan 2001||Automotive Technologies International Inc.||On board vehicle diagnostic module using pattern recognition|
|US6304862||20 Oct 1999||16 Oct 2001||Yamaha Hatsudoki Kabushiki Kaisha||Evolutionary controlling system|
|US6314412 *||24 Sep 1998||6 Nov 2001||Yamaha Hatsudoki Kabushiki Kaisha||Evolutionary control of machine based on user's preference inferred from user's operation|
|US6321151 *||12 May 2000||20 Nov 2001||Paul Shultz||Automotive diagnostic interface device|
|US6326704||16 Jul 1999||4 Dec 2001||Automotive Technologies International Inc.||Vehicle electrical system|
|US6330499||21 Jul 1999||11 Dec 2001||International Business Machines Corporation||System and method for vehicle diagnostics and health monitoring|
|US6408242||22 Jun 2000||18 Jun 2002||Cummins, Inc.||Apparatus and method for diagnosing and controlling an ignition system of an internal combustion engine|
|US6477478||27 Aug 1999||5 Nov 2002||Snap-On Equipment Limited||Method and apparatus for automotive and other testing|
|US6484080||2 Jan 2001||19 Nov 2002||Automotive Technologies International Inc.||Method and apparatus for controlling a vehicular component|
|US6533316||23 Jan 2001||18 Mar 2003||Automotive Technologies International, Inc.||Automotive electronic safety network|
|US6556951||24 Nov 1998||29 Apr 2003||The United States Of America As Represented By The Secretary Of The Department Of Health And Human Services||System and method for intelligent quality control of a process|
|US6571191||27 Oct 1998||27 May 2003||Cummins, Inc.||Method and system for recalibration of an electronic control module|
|US6574613 *||24 Feb 1999||3 Jun 2003||Jorge Moreno-Barragan||System and method for diagnosing jet engine conditions|
|US6604032 *||30 Mar 1998||5 Aug 2003||Volvo Personvagnar Ab||Diagnostic system in an engine management system|
|US6648367||26 Jan 2001||18 Nov 2003||Automotive Technologies International Inc.||Integrated occupant protection system|
|US6701282 *||20 Sep 2001||2 Mar 2004||General Motors Corporation||Fault identification diagnostic for intake system sensors|
|US6718251||29 Jan 2002||6 Apr 2004||Cummins, Inc.||System for controlling exhaust emissions produced by an internal combustion engine|
|US6733036||8 Aug 2001||11 May 2004||Automotive Technologies International, Inc.||Automotive electronic safety network|
|US6738697||3 Jul 2002||18 May 2004||Automotive Technologies International Inc.||Telematics system for vehicle diagnostics|
|US6823244||27 Dec 2002||23 Nov 2004||Automotive Technologies International, Inc.||Vehicle part control system including electronic sensors|
|US6850824||3 Jul 2003||1 Feb 2005||Automotive Technologies International, Inc.||Method and apparatus for controlling a vehicular component|
|US6954693||30 Mar 2004||11 Oct 2005||Cummins, Inc.||System for controlling exhaust emissions produced by an internal combustion engine|
|US7031950 *||14 Dec 2001||18 Apr 2006||Siemens Corporate Research, Inc.||Method and apparatus for providing a virtual age estimation for remaining lifetime prediction of a system using neural networks|
|US7082359||19 Jan 2005||25 Jul 2006||Automotive Technologies International, Inc.||Vehicular information and monitoring system and methods|
|US7103460||6 Sep 2005||5 Sep 2006||Automotive Technologies International, Inc.||System and method for vehicle diagnostics|
|US7130768 *||18 Oct 2004||31 Oct 2006||Siemens Aktiengesellschaft||Method and device for fault diagnosis in control systems in an internal combustion engine in a motor vehicle|
|US7328625||16 Sep 2005||12 Feb 2008||Caterpillar Inc.||Systems and methods for determining fatigue life|
|US7472599||30 Jun 2006||6 Jan 2009||Caterpillar Inc.||Strain sensing device|
|US7487066||16 Sep 2005||3 Feb 2009||Caterpillar Inc.||Classifying a work machine operation|
|US7527288||5 Sep 2006||5 May 2009||Automotive Technologies International, Inc.||Vehicle with crash sensor coupled to data bus|
|US7630802||5 Jun 2006||8 Dec 2009||Automotive Technologies International, Inc.||Information management and monitoring system and method|
|US7635043 *||27 Dec 2002||22 Dec 2009||Automotive Technologies International, Inc.||Crash sensor arrangement for controlling deployment of an occupant restraint device|
|US7650210||14 Aug 2006||19 Jan 2010||Automotive Technologies International, Inc.||Remote vehicle diagnostic management|
|US7672756||1 Jun 2006||2 Mar 2010||Automotive Technologies International, Inc.||Vehicle communications using the internet|
|US7702435||19 Oct 2005||20 Apr 2010||Honeywell International Inc.||Method and apparatus for system monitoring and maintenance|
|US7908928||31 Oct 2006||22 Mar 2011||Caterpillar Inc.||Monitoring system|
|US7937197 *||7 Jan 2005||3 May 2011||GM Global Technology Operations LLC||Apparatus and methods for evaluating a dynamic system|
|US7953559||16 Sep 2005||31 May 2011||Caterpillar Inc.||Systems and methods for maintaining load histories|
|US8019501||2 Aug 2007||13 Sep 2011||Automotive Technologies International, Inc.||Vehicle diagnostic and prognostic methods and systems|
|US8024084||31 Oct 2007||20 Sep 2011||Automotive Technologies International, Inc.||Vehicle diagnostic techniques|
|US8036788||9 Aug 2007||11 Oct 2011||Automotive Technologies International, Inc.||Vehicle diagnostic or prognostic message transmission systems and methods|
|US8060282||2 Aug 2007||15 Nov 2011||Automotive Technologies International, Inc.||Vehicle component control methods and systems based on vehicle stability|
|US8151654||3 Oct 2006||10 Apr 2012||Methode Electronics, Inc.||Sensor pad for controlling airbag deployment and associated support|
|US8157047||21 Feb 2008||17 Apr 2012||Automotive Technologies International, Inc.||Occupant protection systems control techniques|
|US8169311||5 Mar 2007||1 May 2012||Automotive Technologies International, Inc.||Wireless transmission system for vehicular component control and monitoring|
|US8229620||15 May 2006||24 Jul 2012||Robert Bosch Gmbh||Method for model-based diagnosis of a mechatronic system|
|US8229624||21 Feb 2008||24 Jul 2012||American Vehicular Sciences Llc||Vehicle diagnostic information generating and transmission systems and methods|
|US8239122 *||15 Jul 2008||7 Aug 2012||Ford Global Technologies, Llc||Vehicle surge and spark timing control|
|US8290661 *||20 Nov 2008||16 Oct 2012||Hyundai Motor Company||Simulation test system and method for testing vehicle electronic component|
|US8352164||6 Aug 2012||8 Jan 2013||Ford Global Technologies, Llc||Vehicle surge and spark timing control|
|US8374745 *||5 Sep 2008||12 Feb 2013||GM Global Technology Operations LLC||Telematics-enabled aggregated vehicle diagnosis and prognosis|
|US8416067||9 Sep 2009||9 Apr 2013||United Parcel Service Of America, Inc.||Systems and methods for utilizing telematics data to improve fleet management operations|
|US8673137||9 Mar 2011||18 Mar 2014||Cummins Filtration Ip, Inc.||Apparatus, system and method for detecting the presence of genuine serviceable product components|
|US8768573||11 Oct 2012||1 Jul 2014||American Vehicular Sciences, LLC||Technique for ensuring safe travel of a vehicle or safety of an occupant therein|
|US8896430||13 Mar 2013||25 Nov 2014||United Parcel Service Of America, Inc.||Systems and methods for utilizing telematics data to improve fleet management operations|
|US8897953||26 Jul 2012||25 Nov 2014||United Parcel Service Of America, Inc.||Systems and methods for managing fault codes|
|US8898525||17 Apr 2012||25 Nov 2014||General Electric Company||Method and system for use in condition monitoring|
|US9020684 *||24 Jan 2012||28 Apr 2015||Continental Automotive Gmbh||Method, system and computer programme product for monitoring the function of a safety monitoring system of a control unit|
|US9022417||14 Oct 2013||5 May 2015||American Vehicular Sciences Llc||Single side curtain airbag for vehicles|
|US9026304||7 Apr 2009||5 May 2015||United Parcel Service Of America, Inc.||Vehicle maintenance systems and methods|
|US9208626||30 Nov 2011||8 Dec 2015||United Parcel Service Of America, Inc.||Systems and methods for segmenting operational data|
|US9256992||30 Mar 2012||9 Feb 2016||United Parcel Service Of America, Inc.||Systems and methods for assessing vehicle handling|
|US9292979||23 Oct 2014||22 Mar 2016||United Parcel Service Of America, Inc.||Systems and methods for managing fault codes|
|US9324198||27 Feb 2015||26 Apr 2016||United Parcel Service Of America, Inc.||Systems and methods for utilizing telematics data to improve fleet management operations|
|US9342933||24 Mar 2015||17 May 2016||United Parcel Service Of America, Inc.||Vehicle maintenance systems and methods|
|US9443358||31 Oct 2007||13 Sep 2016||Automotive Vehicular Sciences LLC||Vehicle software upgrade techniques|
|US9447745 *||15 Sep 2011||20 Sep 2016||General Electric Company||System and method for diagnosing an engine|
|US9472030||27 Feb 2015||18 Oct 2016||United Parcel Service Of America, Inc.||Systems and methods for utilizing telematics data to improve fleet management operations|
|US9597620||30 Jan 2014||21 Mar 2017||Cummins Filtration Ip, Inc.||Apparatus, system and method for detecting the presence of genuine serviceable product components|
|US9613468||30 Mar 2012||4 Apr 2017||United Parcel Service Of America, Inc.||Systems and methods for updating maps based on telematics data|
|US9704303||17 Oct 2014||11 Jul 2017||United Parcel Service Of America, Inc.||Systems and methods for utilizing telematics data to improve fleet management operations|
|US9740993 *||4 Dec 2009||22 Aug 2017||GM Global Technology Operations LLC||Detecting anomalies in field failure data|
|US20040039509 *||3 Jul 2003||26 Feb 2004||Breed David S.||Method and apparatus for controlling a vehicular component|
|US20040059694 *||14 Dec 2001||25 Mar 2004||Darken Christian J.||Method and apparatus for providing a virtual age estimation for remaining lifetime prediction of a system using neural networks|
|US20040186655 *||30 Mar 2004||23 Sep 2004||Brackney Larry J.||System for controlling exhaust emissions produced by an internal combustion engine|
|US20040260454 *||14 Jun 2004||23 Dec 2004||Basir Otman A.||Vibro-acoustic engine diagnostic system|
|US20050114087 *||18 Oct 2004||26 May 2005||Siemens Aktiengesellschaft||Method and device for fault diagnosis in control systems in an internal combustion engine in a motor vehicle|
|US20050125117 *||19 Jan 2005||9 Jun 2005||Breed David S.||Vehicular information and monitoring system and methods|
|US20060126608 *||19 Oct 2005||15 Jun 2006||Honeywell International Inc.||Method and apparatus for system monitoring and maintenance|
|US20060155734 *||7 Jan 2005||13 Jul 2006||Grimes Michael R||Apparatus and methods for evaluating a dynamic system|
|US20060212194 *||1 Jun 2006||21 Sep 2006||Automotive Technologies International, Inc.||Vehicle Communications Using the Internet|
|US20060229777 *||11 Apr 2006||12 Oct 2006||Hudson Michael D||System and methods of performing real-time on-board automotive telemetry analysis and reporting|
|US20060243056 *||16 Sep 2005||2 Nov 2006||Sundermeyer Jeffry N||Systems and methods for maintaining load histories|
|US20060243180 *||16 Sep 2005||2 Nov 2006||Sundermeyer Jeffry N||Classifying a work machine operation|
|US20070005202 *||14 Aug 2006||4 Jan 2007||Automotive Technologies International, Inc.||Remote Vehicle Diagnostic Management|
|US20070075919 *||5 Sep 2006||5 Apr 2007||Breed David S||Vehicle with Crash Sensor Coupled to Data Bus|
|US20070271014 *||2 Aug 2007||22 Nov 2007||Automotive Technologies International, Inc.||Vehicle Diagnostic and Prognostic Methods and Systems|
|US20080011085 *||30 Jun 2006||17 Jan 2008||Caterpillar Inc.||Strain sensing device|
|US20080040005 *||2 Aug 2007||14 Feb 2008||Automotive Technologies International, Inc.||Vehicle Component Control Methods and Systems Based on Vehicle Stability|
|US20080046149 *||2 Aug 2007||21 Feb 2008||Automotive Technologies International, Inc.||Vehicle Component Control Methods and Systems Based on Vehicle Stability|
|US20080147265 *||9 Aug 2007||19 Jun 2008||Automotive Technologies International, Inc.||Vehicle Diagnostic or Prognostic Message Transmission Systems and Methods|
|US20080147271 *||21 Feb 2008||19 Jun 2008||Automotives Technologies International, Inc.||Vehicle Component Control Methods and Systems|
|US20080147280 *||11 Feb 2008||19 Jun 2008||Automotive Technologies International, Inc.||Method and apparatus for sensing a rollover|
|US20080161989 *||9 Aug 2007||3 Jul 2008||Automotive Technologies International, Inc.||Vehicle Diagnostic or Prognostic Message Transmission Systems and Methods|
|US20080255773 *||18 Mar 2008||16 Oct 2008||Chao Yuan||Machine condition monitoring using pattern rules|
|US20080284575 *||31 Oct 2007||20 Nov 2008||Automotive Technologies International, Inc.||Vehicle Diagnostic Techniques|
|US20090153315 *||20 Nov 2008||18 Jun 2009||Hyundai Motor Company||Method for diagnosing error of vehicle electronic component|
|US20090157374 *||20 Nov 2008||18 Jun 2009||Hyundai Motor Company||Simulation test system and method for testing vehicle electronic component|
|US20090187303 *||15 May 2006||23 Jul 2009||Robert Bosch Gmbh||Method For Model-Based Diagnosis Of A Mechatronic System|
|US20100017101 *||15 Jul 2008||21 Jan 2010||Ford Global Technologies, Llc||Vehicle surge and spark timing control|
|US20100030418 *||31 Jul 2008||4 Feb 2010||Gm Global Technology Operations, Inc.||Online health monitoring via multidimensional temporal data mining|
|US20100063668 *||5 Sep 2008||11 Mar 2010||Gm Global Technology Operations, Inc.||Telematics-enabled aggregated vehicle diagnosis and prognosis|
|US20100100338 *||31 Oct 2006||22 Apr 2010||Caterpillar Inc.||Monitoring system|
|US20100217498 *||24 Oct 2008||26 Aug 2010||Bilal Youssef||Engine control method based on graphic signatures|
|US20110137711 *||4 Dec 2009||9 Jun 2011||Gm Global Technology Operations, Inc.||Detecting anomalies in field failure data|
|US20110220560 *||9 Mar 2011||15 Sep 2011||Cummins Filtration Ip, Inc.||Apparatus, system and method for detecting the presence of genuine serviceable product components|
|US20110231316 *||9 Mar 2011||22 Sep 2011||Cummins Intellectual Properties, Inc.||Method, system and computer readable media containing a program for identifying whether a product is genuine|
|US20110307217 *||22 Aug 2011||15 Dec 2011||Avl List Gmbh||Method and apparatus for analysis and assessment of measurement data of a measurement system|
|US20130073174 *||15 Sep 2011||21 Mar 2013||Bret Dwayne Worden||System and method for diagnosing an engine|
|US20130196294 *||28 Jan 2012||1 Aug 2013||Ganapathy Lakshmanaperumal||Automotive troubleshooting instructor|
|US20140012463 *||24 Jan 2012||9 Jan 2014||Bernd Pfaffeneder||Method, system and computer programme product for monitoring the function of a safety monitoring system of a control unit|
|US20160025027 *||14 Mar 2014||28 Jan 2016||Angel Enterprise Systems, Inc.||Engine analysis and diagnostic system|
|CN101189500B||15 May 2006||19 May 2010||罗伯特·博世有限公司||Method for the model-based diagnosis of a mechatronic system|
|CN102869972A *||9 Mar 2011||9 Jan 2013||康明斯过滤Ip公司||Apparatus, system and method for detecting the presence of genuine serviceable product components|
|DE4340746C2 *||30 Nov 1993||27 Nov 2003||Toyota Chuo Kenkyusho Aichi Kk||Diagnoseeinrichtung zum Diagnostizieren eines dynamischen Systems|
|EP0637739A2 *||15 Jul 1994||8 Feb 1995||Ford Motor Company Limited||Testing an internal combustion engine|
|EP0637739A3 *||15 Jul 1994||6 Dec 1995||Ford Motor Co||Testing an internal combustion engine.|
|EP0695668A1||13 Jul 1995||7 Feb 1996||Delco Electronics Corporation||Supplemental inflatable restraint system|
|EP0838674A2 *||22 Oct 1997||29 Apr 1998||Schenck Process GmbH||Method for evaluating vibration signals of technical systems|
|EP0838674A3 *||22 Oct 1997||14 Apr 1999||Schenck Process GmbH||Method for evaluating vibration signals of technical systems|
|EP0922856A2 *||3 Dec 1998||16 Jun 1999||Cummins Engine Company, Inc.||Apparatus and method for diagnosing and controlling an ignition system of an internal combustion engine|
|EP0922856A3 *||3 Dec 1998||7 Feb 2001||Cummins Engine Company, Inc.|
|EP1117023A2 *||28 Dec 2000||18 Jul 2001||Robert Bosch Gmbh||Device for fault diagnosis during motor vehicle operation|
|EP1117023A3 *||28 Dec 2000||30 Jul 2003||Robert Bosch Gmbh||Device for fault diagnosis during motor vehicle operation|
|EP1574864A1 *||18 Feb 2005||14 Sep 2005||Audi Ag||Method for testing of the function of electronic and electric components mounted in a vehicle of a specific type and addressable via a communication bus|
|WO1993024751A2 *||24 May 1993||9 Dec 1993||Ford Motor Company Limited||Misfire detection in an internal combustion engine using exhaust pressure|
|WO1993024751A3 *||24 May 1993||17 Mar 1994||Ford Werke Ag||Misfire detection in an internal combustion engine using exhaust pressure|
|WO1997008642A1 *||22 Aug 1996||6 Mar 1997||The Ohio State University Research Foundation||Methods and apparatus for performing combustion analysis in an internal combustion engine utilizing ignition voltage analysis|
|WO1997013064A2 *||3 Oct 1996||10 Apr 1997||Ab Volvo||Diagnostic system particularly for an engine management system|
|WO1997013064A3 *||3 Oct 1996||5 Jun 1997||Volvo Ab||Diagnostic system particularly for an engine management system|
|WO2001035257A1 *||10 Nov 2000||17 May 2001||Microsoft Corporation||Determining similarity between event types in sequences|
|WO2004101300A1 *||10 May 2004||25 Nov 2004||Conti Temic Microelectronic Gmbh||Method for detection and monitoring of the movements of vehicles|
|WO2006116758A2 *||28 Apr 2006||2 Nov 2006||Caterpillar Inc.||Systems and methods for maintaining load histories|
|WO2006116758A3 *||28 Apr 2006||11 Jan 2007||Caterpillar Inc||Systems and methods for maintaining load histories|
|WO2006128788A1 *||15 May 2006||7 Dec 2006||Robert Bosch Gmbh||Method for the model-based diagnosis of a mechatronic system|
|WO2011112702A2 *||9 Mar 2011||15 Sep 2011||Cummins Filtration Ip, Inc.||Apparatus, system and method for detecting the presence of genuine serviceable product components|
|WO2011112702A3 *||9 Mar 2011||29 Dec 2011||Cummins Filtration Ip, Inc.||Apparatus, system and method for detecting the presence of genuine serviceable product components|
|U.S. Classification||701/32.9, 706/911, 701/102, 701/29.1, 701/34.4, 701/33.6|
|International Classification||G01R31/00, F02D41/22|
|Cooperative Classification||Y10S706/911, G01R31/007, F02D41/1405, F02D41/22, Y02T10/40|
|European Classification||G01R31/00T2B, F02D41/22|
|20 Nov 1989||AS||Assignment|
Owner name: FORD MOTOR COMPANY, MICHIGAN
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST.;ASSIGNORS:MARKO, KENNETH A.;JAMES, JOHN V.;DOSDALL, JAMES M.;REEL/FRAME:005182/0885;SIGNING DATES FROM 19890811 TO 19890815
|28 Mar 1995||REMI||Maintenance fee reminder mailed|
|20 Aug 1995||LAPS||Lapse for failure to pay maintenance fees|
|31 Oct 1995||FP||Expired due to failure to pay maintenance fee|
Effective date: 19950823